Wan2.2 - Ultimate SD Image Upscaler - Batch loader - Florence - Master UI
Runtime profile
Source description
Wan2.2 - Ultimate SD Image Upscaler - Batch loader - Florence - Master UI
Upscale Model - https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth
Clip -
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This workflow is for image upscaling. It can load single images or image batches, process prompt text with Florence, and save image outputs; its graph also includes WanImageToVideo.
The listed steps cover image loading, batch loading, prompt replacement, text concatenation, Florence runs, scaling, model-based upscaling, image comparison, and saving.
The graph also includes CLIP loading, text encoding, resolution controls, and WanImageToVideo.
LoadImage and Load Image Batch identify single-image and batch-image inputs.
CLIPTextEncode, Text Concatenate, and Florence2Run are listed for text processing; SaveImage is listed for image output, and Image Comparer (rgthree) is listed for image comparison.
The workflow is listed on Civitai as a Workflow and is published by Sinusplusminus.
Listed model files are lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16_.safetensors, MiaoshouAI/Florence-2-base-PromptGen-v2.0, RealESRGAN_x2plus.pth, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, and Wan2_2-T2V-A14B-LOW_fp8_e4m3fn_scaled_KJ.safetensors.
Listed node packs are comfyui_tinyterranodes, comfyui_ultimatesdupscale, comfyui-easy-use, comfyui-florence2, comfyui-workflow-encrypt, crt-nodes, and was-ns.
The listed base model is Wan Video 2.2 I2V-A14B.
Listed node-pack pins are comfyui_tinyterranodes 2.0.9, comfyui_ultimatesdupscale 1.5.1, comfyui-easy-use 5c8cdb58c798a404e50636c6f3e179b084a23fab, and comfyui-florence2 1.0.3.
The remaining listed pins are comfyui-workflow-encrypt 1.0.0, crt-nodes 1.9.6, and was-ns 3.0.1.
Before setup, verify the source and exact file for wan_2.1_vae.safetensors, lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16_.safetensors, Wan2_2-T2V-A14B-LOW_fp8_e4m3fn_scaled_KJ.safetensors, and umt5_xxl_fp8_e4m3fn_scaled.safetensors; no source URL is listed for these four
Suggestion · not verified
Before setup, confirm the exact comfyui-florence2 pack and RealESRGAN_x2plus.pth file, and verify where to obtain was-ns.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 204 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Estimated VRAM requirement
Estimate unavailable
14.0 GB across 1 of 7 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
13 requirementsUpscaler · Registry · ComfyUI_UltimateSDUpscale
lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16_.safetensors
Not resolvedLoRA · Unknown
MiaoshouAI/Florence-2-base-PromptGen-v2.0
File unverifiedVision model · Hugging Face · MiaoshouAI/Florence-2-base-PromptGen-v2.0 · Florence 2 Base PromptGen v2.0
RealESRGAN_x2plus.pth
ConflictUpscaler · Unknown
umt5_xxl_fp8_e4m3fn_scaled.safetensors
File unverifiedText encoder · SAFETENSORS · Unknown
VAE · Unknown
Checkpoint · 14.0 GB · SAFETENSORS · fp8 · pruned · Unknown
Node pack · Registry
Node pack · Registry
comfyui-florence2
Node pack · Registry
Node pack · Registry
Node pack · Registry
was-ns
Not resolvedNode pack · Registry